{"id":"https://openalex.org/W3008337170","doi":"https://doi.org/10.1109/bigdata47090.2019.9006135","title":"Constructing Suffix Array of Next-Generation Sequencing upon In-Memory Lookup Cloud and MapReduce","display_name":"Constructing Suffix Array of Next-Generation Sequencing upon In-Memory Lookup Cloud and MapReduce","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008337170","doi":"https://doi.org/10.1109/bigdata47090.2019.9006135","mag":"3008337170"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027285229","display_name":"Liu Li-Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Chen Liu","raw_affiliation_strings":["Department of Engineering Science and Ocean Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science and Ocean Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001067457","display_name":"Meng\u2010Huang Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I14140830","display_name":"Shih Chien University","ror":"https://ror.org/01c3hyk82","country_code":"TW","type":"education","lineage":["https://openalex.org/I14140830"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Meng-Huang Lee","raw_affiliation_strings":["Department of Information Technology and Management, Shih Chien University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology and Management, Shih Chien University, Taipei, Taiwan","institution_ids":["https://openalex.org/I14140830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103349260","display_name":"Shin-Hung Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I114150738","display_name":"Fu Jen Catholic University","ror":"https://ror.org/04je98850","country_code":"TW","type":"education","lineage":["https://openalex.org/I114150738"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shin-Hung Chang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Fu Jen Catholic University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Fu Jen Catholic University, Taipei, Taiwan","institution_ids":["https://openalex.org/I114150738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043595446","display_name":"Ray-I Chang","orcid":"https://orcid.org/0000-0002-8737-7227"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ray-I Chang","raw_affiliation_strings":["Department of Engineering Science and Ocean Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science and Ocean Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043842260","display_name":"Yu-Jung Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jung Chang","raw_affiliation_strings":["Institute of Information Science Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051317071","display_name":"Jan-Ming Ho","orcid":"https://orcid.org/0000-0002-2432-8233"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jan-Ming Ho","raw_affiliation_strings":["Institute of Information Science Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19993874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3373","last_page":"3378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.9187077283859253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8404743671417236},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.8239144086837769},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6994876265525818},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.5492593050003052},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5187309384346008},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4958523213863373},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.47767147421836853},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.4636816382408142},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.435257226228714},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18865731358528137},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07799658179283142}],"concepts":[{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.9187077283859253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8404743671417236},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.8239144086837769},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6994876265525818},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.5492593050003052},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5187309384346008},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4958523213863373},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.47767147421836853},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.4636816382408142},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.435257226228714},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18865731358528137},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07799658179283142},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2061680337","https://openalex.org/W2063431258","https://openalex.org/W2063556310","https://openalex.org/W2134283755","https://openalex.org/W2163430637"],"related_works":["https://openalex.org/W2003608043","https://openalex.org/W2405892617","https://openalex.org/W153119118","https://openalex.org/W2583658747","https://openalex.org/W4293529780","https://openalex.org/W2158874082","https://openalex.org/W1575722140","https://openalex.org/W2073921136","https://openalex.org/W1965532872","https://openalex.org/W3092594492"],"abstract_inverted_index":{"TeraSort":[0,27,274],"[7]":[1],"is":[2,8,164,219],"a":[3,11,69,72,111,149,182,185,191],"standard":[4],"MapReduce":[5,51,231],"sort":[6,18],"which":[7],"applied":[9],"as":[10,45,91],"benchmark":[12],"to":[13,17,28,39,80,88,109,137,169,189,210],"measure":[14],"the":[15,46,50,58,61,81,92,98,115,124,153,156,171,176,196,199,204,213,233,242,246,253,267,270],"time":[16,248,255,268],"terabytes":[19],"of":[20,49,56,60,132,155,178,201,215,235,249,256,273],"randomly":[21],"distributed":[22],"data.":[23],"TeraSuffix":[24,38,103],"[5]":[25],"adopts":[26,105],"construct":[29,40],"suffix":[30,41,73,90,112,125,197,216,277],"array":[31,42],"for":[32,43,140,275],"NGS":[33,82,116,172],"(Next-Generation":[34],"Sequencing).":[35],"When":[36,184],"using":[37],"NGS,":[44],"intermediate":[47,62,93],"data":[48,63,94,118,174,250],"framework":[52],"contains":[53],"multiple":[54],"copies":[55],"suffixes,":[57],"shuffle":[59,99],"between":[64],"map":[65],"and":[66,95,113,252,261,269],"reduce":[67,97,127,257],"become":[68,148],"bottleneck.":[70,150],"For":[71],"can":[74,194],"be":[75],"represented":[76],"by":[77,259],"its":[78],"index":[79,107],"Reads":[83,117,173],"data,":[84],"it's":[85],"no":[86],"need":[87,130],"record":[89],"thus":[96],"time.":[100],"Disk-based":[101,157],"Indexed":[102,158],"[6]":[104],"this":[106,167],"structure":[108],"represent":[110],"stores":[114],"on":[119,175,228],"disk.":[120,223],"However,":[121],"when":[122],"constructing":[123,276],"array,":[126],"tasks":[128,258],"still":[129],"lots":[131],"random":[133],"access":[134,195,214],"from":[135,198,222],"disk":[136,145],"retrieve":[138,190],"suffixes":[139],"further":[141],"processing.":[142],"The":[143],"massive":[144],"I/O":[146],"operations":[147],"To":[151],"increase":[152],"efficiency":[154,272],"TeraSuffix,":[159],"in-memory":[160],"lookup":[161],"cloud":[162],"(MLC)":[163],"proposed":[165,243],"in":[166,181],"paper":[168],"store":[170],"memory":[177,200],"remote":[179],"servers":[180],"cloud.":[183],"map/reduce":[186],"task":[187],"needs":[188],"suffix,":[192],"it":[193],"MLC":[202],"through":[203,217],"network.":[205],"Experimental":[206],"tests":[207],"were":[208,225],"performed":[209,227],"show":[211],"that":[212,241],"network":[218],"outperformed":[220],"than":[221],"Experiments":[224],"also":[226],"Amazon":[229],"Elastic":[230],"with":[232],"sequence":[234],"20Gbp-Grouper":[236],"(about":[237],"20Gbytes).":[238],"It":[239,264],"showed":[240],"architecture":[244],"reduces":[245],"pre-processing":[247],"replication":[251],"processing":[254],"58%":[260],"8%,":[262],"respectively.":[263],"improves":[265],"both":[266],"space":[271],"array.":[278]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
